© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50366
    Prev
    Next
    INDEX
    Explanations

    loyal or faithful relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleg
    -0.10
    engl
    -0.10
     ginger
    -0.09
     elegant
    -0.09
    het
    -0.09
     elegance
    -0.09
     genom
    -0.09
    /interface
    -0.08
    owell
    -0.08
    æ¬
    -0.08
    POSITIVE LOGITS
     loyalty
    0.23
     Loy
    0.22
     fidelity
    0.21
     faithfully
    0.20
     devotion
    0.20
     faithful
    0.20
     loyal
    0.18
     allegiance
    0.17
    loy
    0.16
     duty
    0.15
    Activations Density 0.032%

    No Known Activations